ROS2-based automobile driving assistance system test device and test method

Abstract

The invention discloses an automobile driving assistance system testing device and method based on ROS2, and relates to the field of automobile driving assistance system testing, and the device comprises a multidirectional vision collection module which is used for collecting image data in front of and behind the side of an automobile; the attitude sensing module is used for collecting attitude data in the vehicle driving process; the man-machine interaction module is used for inputting an operation instruction in the test process of the automobile driving assistance system and executing the test of the automobile driving assistance system in each scene; the data processing and storage module carries an operating system for running ROS2 middleware, and is used for driving the multidirectional vision acquisition module and the attitude sensing module according to the operation instruction, and receiving and storing the image data and the attitude data; the power supply module is used for supplying power to the automobile driving assistance system testing device; the power supply module is a vehicle cigarette lighter or an independent power supply. The device provided by the invention is light in weight, portable, low in cost and rapid in deployment, and supports synchronous acquisition and expansion of multiple sensors.

Description

Technical Field

[0001] This application relates to the field of testing advanced driver assistance systems (ADAS), and in particular to a testing device and method for automotive driver assistance systems based on ROS2. Background Technology

[0002] In recent years, ADAS technology has developed rapidly, and the pace of technological iteration has accelerated. As a result, automobile companies have an increasing need to conduct evaluation and analysis of ADAS system solutions from competitors in the market during the development of new models. Extensive evaluation of solutions is used to guide the definition of vehicle ADAS equipment, functions, and performance-related indicators to ensure product competitiveness.

[0003] Current traditional ADAS testing relies on dedicated data acquisition systems. While these systems can collect data from sensors and vehicle signals to form timestamped data streams, they are typically expensive, complex, bulky, and time-consuming to install and deploy, making them suitable only for long-term road testing during the development phase. However, ADAS solution evaluation usually requires the use of competitor vehicles, and time is extremely tight, making it impossible to conduct the work using traditional data acquisition equipment. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a lightweight, portable, low-cost, rapidly deployable ROS2-based automotive driver assistance system testing device and method that supports simultaneous acquisition and expansion of multiple sensors.

[0005] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a testing device for an automotive driving assistance system based on ROS2, comprising: The multi-directional vision acquisition module is used to acquire image data from the front and sides / rear of the vehicle. The attitude perception module is used to collect attitude data during vehicle movement; the attitude data includes acceleration data, angular velocity data, and attitude angle data. The human-computer interaction module is used to input operation commands during the testing of automotive driver assistance systems and to execute tests of the automotive driver assistance systems in various scenarios. The data processing and storage module is connected to the multi-directional vision acquisition module, the posture perception module and the human-computer interaction module respectively. It is equipped with an operating system running ROS2 middleware and is used to drive the multi-directional vision acquisition module and the posture perception module according to the operation instructions, and to receive and store the image data and the posture data. A power supply module is used to supply power to the vehicle driving assistance system test device; the power supply module is a vehicle cigarette lighter or an independent power source.

[0006] Secondly, this application provides a ROS2-based testing method for automotive driver assistance systems, the method being applied to the aforementioned ROS2-based automotive driver assistance system testing device, the method comprising: The aforementioned ROS2-based automotive driver assistance system test device was deployed at a designated location on the vehicle. Start the data processing and storage module and load the ROS2 environment, then run the sensor driver node; Start the rosbag2 recording task, subscribe to the topics corresponding to the multi-directional vision acquisition module and the posture perception module, synchronously collect and store image data and posture data, and execute tests of the car driving assistance system in various test scenarios.

[0007] According to the specific embodiments provided in this application, this application has the following technical effects: (1) Lightweight and portable: The power supply module that powers the whole device in this application uses the vehicle cigarette lighter or an independent power supply, without relying on the vehicle-mounted dedicated power supply. It is compatible with the power supply interface of different vehicle models, reducing the dependence of deployment on vehicles, further improving deployment flexibility and convenience, and improving deployment efficiency. The simplification of the overall architecture solves the problems of large size and difficult transportation and installation of traditional equipment.

[0008] (2) Test cost is greatly reduced: The hardware of the device in this application uses general modules, eliminating the need for customized expensive components, which greatly reduces the device cost and ADAS test cost.

[0009] (3) Reliable synchronization of multi-source data: The data processing and storage module in this application is equipped with an operating system running ROS2 middleware. Through the DDS mechanism of ROS2, the real-time communication of each node is ensured, and the image data and vehicle attitude data are aligned in time, providing a reliable basis for subsequent ADAS behavior analysis.

[0010] (4) Flexible and expandable functions: It supports the expansion of sensors such as cameras and microphones through USB interface / CSI interface to adapt to different test scenario requirements and get rid of the limitations of traditional equipment hardware fixed and poor expandability. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1This is a schematic diagram of the functional modules of a test device for an automotive driving assistance system based on ROS2, provided in one embodiment of this application.

[0013] Figure 2 This is a schematic diagram of data acquisition and synchronization.

[0014] Figure 3 This is a schematic diagram of the test scenario.

[0015] Figure 4 This is a schematic diagram of the vehicle speed curve when following another vehicle at low speed in ADAS mode.

[0016] Figure 5 A schematic diagram of acceleration and deceleration curves when following another vehicle at low speed in ADAS mode.

[0017] Figure 6 For the cut Figure 4 A schematic diagram of vehicle speed curves for a portion of the time period.

[0018] Figure 7 For the cut Figure 5 A schematic diagram of acceleration and deceleration curves for a portion of the time period. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] In one exemplary embodiment, such as Figure 1 As shown, a test device for an automotive driving assistance system based on ROS2 is provided, including: a multi-directional vision acquisition module 1, a posture perception module 2, a human-computer interaction module 3, a data processing and storage module 4, and a power supply module 5.

[0022] The multi-directional vision acquisition module 1 is used to acquire image data from the front and sides / rear of the vehicle. In this embodiment, the multi-directional vision acquisition module 1 includes: one industrial long-range camera and two industrial short-range cameras. The industrial long-range camera is positioned in front of the rearview mirror and is used to acquire image data from the front of the vehicle. Specifically, the industrial long-range camera acquires long-distance environmental images within a 120° forward field of view of the vehicle. The industrial short-range cameras are respectively installed below the left and right exterior rearview mirrors of the vehicle and are used to acquire image data from the sides / rear of the vehicle. Specifically, the industrial short-range cameras acquire close-range environmental images (such as vehicles approaching from the side and lane lines) from the left and right rear of the vehicle.

[0023] The attitude sensing module 2 is used to collect attitude data during vehicle movement. The attitude data includes acceleration data, angular velocity data, and attitude angle data. In this embodiment, the attitude sensing module 2 is a nine-axis IMU unit.

[0024] The human-machine interaction module 3 is used to input operation commands during the testing of the automotive driver assistance system and to execute tests of the automotive driver assistance system in various scenarios. In this embodiment, the human-machine interaction module 3 includes a portable keyboard and a portable touch screen. System initialization, ADAS data acquisition and synchronization, and data playback and analysis during the deployment of the ADAS testing device all require test personnel to operate using the portable keyboard and portable touch screen.

[0025] The data processing and storage module 4 is connected to the multi-directional vision acquisition module 1, the posture perception module 2, and the human-computer interaction module 3, respectively. It is equipped with an operating system running the ROS2 middleware and is used to drive the multi-directional vision acquisition module and the posture perception module according to the operation instructions, and to receive and store the image data and the posture data.

[0026] In this embodiment, the data processing and storage module 4 is the data acquisition host. The operating system is Ubuntu 22.04, and the system middleware is ROS2 Humble LTS. Corresponding ROS nodes are established for the cameras and IMUs in the sensors, and corresponding topics are published. Then, based on the data required for vehicle testing, rosbag2 is used to subscribe to the topics issued by the sensors and record them synchronously. Finally, data analysis is performed through data playback.

[0027] In this embodiment, the data processing and storage module 4 is also provided with a USB interface or a CSI interface for expanding additional sensors.

[0028] The above-mentioned ROS2-based automotive driver assistance system testing device has the following advantages: (1) Lightweight and portable, the whole device weighs only 1KG and does not require an external power source. It can be powered by a cigarette lighter or USB interface. (2) Deployment is quick, and deployment can be completed in 10 minutes, which is suitable for the tight pace of competitor testing; (3) Low cost, with the overall cost being only 1 / 50 of that of traditional road data acquisition instruments; (4) It has strong expandability. Various sensors can be expanded according to needs through USB interface and CSI interface, without being limited by hardware.

[0029] Based on the above-described automotive driver assistance system testing device, in an exemplary embodiment, a ROS2-based automotive driver assistance system testing method is provided, comprising the following steps: S1: Deploy the above-mentioned ROS2-based automotive driver assistance system test device at a designated location on the vehicle.

[0030] The industrial long-focus camera is fixed to the front of the rearview mirror using a suction cup bracket, with the lens facing directly forward to ensure that the field of view covers the unobstructed area of ​​the windshield. Two industrial short-focus cameras are fixed to the lower part of the left and right exterior rearview mirrors respectively using adhesive brackets, with the lenses tilted backward at 30°±5° to ensure coverage of an area within 20m to the side and rear.

[0031] Fix the attitude sensing module 2 and the data processing and storage module 4 to the middle position of the lower trim panel of the front windshield, and calibrate the installation level of the attitude sensing module with a level (error ≤ 0.5°).

[0032] The tester held a portable keyboard and a portable touchscreen, which were powered by power supply module 5.

[0033] S2: Start the data processing and storage module and load the ROS2 environment, and run the sensor driver node.

[0034] System initialization: Start the data processing and storage module 4 to load the ROS2 environment; run the multi-directional vision acquisition module 1 driver node, configure the parameters of the three cameras of the multi-directional vision acquisition module 1, and complete distortion correction and extrinsic parameter calibration through the camera_calibration tool; run the attitude perception module 2 driver node, perform zero bias calibration, and output the fused attitude data.

[0035] S3: Start the rosbag2 recording task, subscribe to the topics corresponding to the multi-directional vision acquisition module 1 and the posture perception module 2, synchronously collect and store image data and posture data, and execute tests of the car driving assistance system in various test scenarios.

[0036] Launch the rosbag2 package for ROS2, and create a recording task, such as... Figure 2As shown, at this time, the nodes of the entire ROS system include the attitude data node (topic: / imu / data) and the image data node (topic: / image_raw), which together constitute the data synchronization recording node (topic: / rosbag2_recorder).

[0037] Using the data synchronization recording node, subscribe to the following topics: Industrial telephoto camera node topic: / camera / front / image_raw; Left rear short-focus camera node topic: / camera / left_rear / image_raw; Right rear short-focus camera node topic: / camera / right_rear / image_raw; Attitude angle data node topic: / euler_angle; Acceleration data node topic: / acc; Angular velocity data node topic: / angle_speed.

[0038] Configure recording parameters, set the time synchronization threshold to ≤50ms (can be adjusted according to actual test requirements), and the data storage format is mcap.

[0039] ADAS testing: Perform ADAS tests under various test scenarios (low-speed following, automatic lane changing, lane keeping, AEB triggering, etc.) according to the test cases.

[0040] After testing, launch Foxglove Studio and import the recorded mcap format data package. Configure the visualization panel to evaluate the functionality of the vehicle's driver assistance system based on attitude and image data. Specifically, evaluate the ADAS functionality by comparing the timing and scenarios of steering and braking commands, along with the corresponding vehicle acceleration / deceleration and angular velocity.

[0041] The following section uses a low-speed following scenario as an example to introduce the use of the aforementioned automotive driver assistance system testing device. The test examples are shown in Table 1, and the test scenarios are as follows: Figure 3 As shown, the vehicle in front is traveling at 20 km / h.

[0042] Table 1

[0043] Tests were conducted according to the test cases, and data was recorded throughout the process using a portable tester. The data playback results are as follows: Figure 4 and Figure 5 As shown. Shorten the time axis and analyze a specific acceleration / deceleration process, such as... Figures 6-7 As shown.

[0044] (1) During the start-up process, there is a two-stage acceleration, which is not a good subjective experience.

[0045] (2) During the process of decelerating and stopping while following another vehicle, there are two stages of deceleration, the deceleration is not continuous, and the subjective feeling is not good.

[0046] (3) During the following process, the deceleration gradient is sometimes too large, and the braking is abrupt.

[0047] (4) There is acceleration oscillation after stopping (i.e.) Figure 7 (The parking oscillation) is manifested as the vehicle nodding.

[0048] Based on the above test results, we can understand the ADAS performance of competing vehicles under different operating conditions, providing empirical data for research and development.

[0049] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A ROS2-based automotive driving assistance system testing device, characterized by, include: The multi-directional vision acquisition module is used to acquire image data from the front and sides / rear of the vehicle. The attitude perception module is used to collect attitude data during vehicle movement; the attitude data includes acceleration data, angular velocity data, and attitude angle data. The human-computer interaction module is used to input operation commands during the testing of automotive driver assistance systems and to execute tests of the automotive driver assistance systems in various scenarios. The data processing and storage module is connected to the multi-directional vision acquisition module, the posture perception module and the human-computer interaction module respectively. It is equipped with an operating system running ROS2 middleware and is used to drive the multi-directional vision acquisition module and the posture perception module according to the operation instructions, and to receive and store the image data and the posture data. The power supply module is used to supply power to the vehicle driving assistance system test device; The power supply module is either the vehicle's cigarette lighter or a separate power source.

2. The ROS2-based automotive driving assistant system testing apparatus according to claim 1, wherein The multi-directional vision acquisition module includes: one industrial long-focus camera and two industrial short-focus cameras; the industrial long-focus camera is positioned in front of the rearview mirror inside the vehicle and is used to acquire image data in front of the vehicle; the industrial short-focus cameras are respectively installed below the left and right exterior rearview mirrors of the vehicle and are used to acquire image data from the sides and rear of the vehicle.

3. The ROS2-based automotive driving assistant system testing apparatus according to claim 1, wherein The attitude sensing module is a nine-axis IMU unit.

4. The ROS2-based automotive driving assistant system testing apparatus according to claim 1, wherein The human-computer interaction module includes a portable keyboard and a portable touchscreen.

5. The ROS2-based automotive driving assistant system testing apparatus of claim 1, wherein, The data processing and storage module is also equipped with a USB interface or CSI interface for expanding additional sensors.

6. A ROS2-based method for testing a car driving assistance system, characterized in that, The method is applied to the ROS2-based automotive driver assistance system testing device according to any one of claims 1-5, and the method includes: The ROS2-based automotive driver assistance system test device according to any one of claims 1-5 is deployed at a designated location on the vehicle; Start the data processing and storage module and load the ROS2 environment, then run the sensor driver node; Start the rosbag2 recording task, subscribe to the topics corresponding to the multi-directional vision acquisition module and the posture perception module, synchronously collect and store image data and posture data, and execute tests of the car driving assistance system in various test scenarios.

7. The ROS2-based automotive driving assistance system testing method of claim 6, wherein, Also includes: The parameters of the multi-directional vision acquisition module are configured, distortion is corrected, and external parameters are calibrated.

8. The ROS2-based automotive driving assistance system testing method of claim 6, wherein, Also includes: Perform zero-bias calibration on the attitude perception module.

9. The ROS2-based automotive driving assistance system testing method of claim 6, wherein, The test scenarios include low-speed following, automatic lane changing, lane keeping, and AEB triggering.

10. The ROS2-based automotive driving assistance system testing method of claim 6, wherein, Also includes: The functionality of the vehicle driver assistance system is evaluated based on the posture data and image data.

Images